© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50915
    Prev
    Next
    INDEX
    Explanations

    phrases at start of sentences

    np_acts-logits-general · gemini-2.5-flash-lite

    Cloud, Augmented Reality, Systems Administrator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haryana
    0.47
     punctures
    0.47
    穿
    0.46
    退
    0.45
     rectangles
    0.44
    潙
    0.44
    下手
    0.44
    洩
    0.44
     swipes
    0.43
    安
    0.43
    POSITIVE LOGITS
    nc
    0.54
     vii
    0.52
     तुझे
    0.50
    numberOfRecords
    0.49
     hice
    0.49
     quang
    0.48
     meiner
    0.48
     selam
    0.48
     deiner
    0.48
    ampton
    0.46
    Activations Density 0.000%

    No Known Activations